© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119593
    Prev
    Next
    INDEX
    Explanations

    references to memory or pointer usage in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inged
    -0.07
    ower
    -0.07
    ä¹
    -0.07
    %s
    -0.06
    Extras
    -0.06
     pyl
    -0.06
    ĨĴ
    -0.06
    alam
    -0.06
    ầm
    -0.06
    ieder
    -0.06
    POSITIVE LOGITS
    amp
    0.11
    nbsp
    0.11
    emsp
    0.09
    quot
    0.09
    rey
    0.07
    athers
    0.07
     amp
    0.07
    oder
    0.07
    åĪ
    0.06
    apos
    0.06
    Activations Density 0.006%

    No Known Activations